TÜRKÇE
ENGLISH
Information
| Unit | INSTITUTE OF NATURAL AND APPLIED SCIENCES |
| REMOTE SENSING AND GEOGRAPHIC INFORMATION SYSTEMS (PhD) | |
| Code | UA606 |
| Name | Classification Methods in Remote Sensing-II |
| Term | 2025-2026 Academic Year |
| Term | Spring |
| Duration (T+A) | 3-0 (T-A) (17 Week) |
| ECTS | 6 ECTS |
| National Credit | 3 National Credit |
| Teaching Language | Türkçe |
| Level | Belirsiz |
| Type | Normal |
| Mode of study | Yüz Yüze Öğretim |
| Catalog Information Coordinator | Prof. Dr. TOLGA ÇAN |
| Course Instructor |
The current term course schedule has not been prepared yet.
|
Course Goal / Objective
Advanced classification techniques, object-oriented analysis approaches and artificial intelligence supported classification methods will be discussed. Using ArcGIS Pro and related advanced tools, object-oriented classification, machine learning and deep learning algorithms, classification processes will be handled practically in different subjects.
Course Content
In order to provide the ability to apply advanced classification methods and modern analysis techniques in the field of remote sensing, this course, which is built on basic classification knowledge, covers classification approaches based on current machine learning and deep learning algorithms such as object-oriented image analysis (OBIA), random forest (Random Forest), support vector machines (SVM), artificial neural networks (ANN) and convolutional neural networks (CNN). In addition, multi-source data integration (e.g. Lidar, SAR, hyperspectral images), temporal change analysis and classification on big data platforms (Google Earth Engine, ArcGIS Image Server) are also included in the course. The course aims to provide students not only technical knowledge but also analytical thinking, algorithm selection and workflow design skills. At the end of the term, students are expected to be able to apply effective classification methods on complex and large data sets and to be able to perform meaningful spatial analyses using advanced software tools.
Course Precondition
There is no pre requires.
Resources
Remote Sensing with ArcGIS Pro (second edition) Copyright © 2023 by Tammy Parece and John McGee.
Notes
Remote Sensing with ArcGIS Pro (second edition) Copyright © 2023 by Tammy Parece and John McGee.
Course Learning Outcomes
| Order | Course Learning Outcomes |
|---|---|
| LO01 | Explain fundamental principles of advanced classification methods. |
| LO02 | Apply object-based image analysis to remote sensing data. |
| LO03 | Use artificial neural network and deep learning algorithms. |
| LO04 | Classify temporal image series |
| LO05 | Enhance classification accuracy using multi-source data. |
Relation with Program Learning Outcome
| Order | Type | Program Learning Outcomes | Level |
|---|---|---|---|
| PLO01 | Bilgi - Kuramsal, Olgusal | At the end of the programme, the students acquire advanced knowledge on remote sensing and GIS theory. | 2 |
| PLO02 | Bilgi - Kuramsal, Olgusal | The students gain knowledge on remote sensing technologies, sensors and platforms and remotely sensed data. | 3 |
| PLO03 | Bilgi - Kuramsal, Olgusal | The students generate information using remotely sensed data and GIS together with database management skills. | 2 |
| PLO04 | Bilgi - Kuramsal, Olgusal | The students develop the necessary skills for selecting and using appropriate techniques and tools for engineering practices, using information technologies effectively, and collecting, analysing and interpreting data. | 2 |
| PLO05 | Bilgi - Kuramsal, Olgusal | The students gain knowledge to use current data and methods for multi-disciplinary research. | 2 |
| PLO06 | Bilgi - Kuramsal, Olgusal | The students gain technical competence and skills in using recent GIS and remote sensing software. | |
| PLO07 | Bilgi - Kuramsal, Olgusal | The students acquire knowledge on potential practical fields of use of remotely sensed data, and use their theoretical and practical knowledge for problem solution in the related professional disciplines. | 2 |
| PLO08 | Yetkinlikler - Öğrenme Yetkinliği | Students will be able to calculate and interpret physical and atmospheric variables by processing the satellite data. | |
| PLO09 | Yetkinlikler - Öğrenme Yetkinliği | Students can generate data for GIS projects using Remote Sensing techniques. | 2 |
| PLO10 | Bilgi - Kuramsal, Olgusal | Gains the ability to analyze and interpret geographic data with GIS techniques. | |
| PLO11 | Bilgi - Kuramsal, Olgusal | Gains the ability of problem solving, solving, solution oriented application development. | 2 |
| PLO12 | Yetkinlikler - Öğrenme Yetkinliği | Acquires the ability to acquire, evaluate, record and apply information from satellite data. |
Week Plan
| Week | Topic | Preparation | Methods |
|---|---|---|---|
| 1 | Introduction to advanced classification concepts | No advance preparation is necessary. | Öğretim Yöntemleri: Anlatım |
| 2 | Object-based image analysis (OBIA) | No advance preparation is necessary. | Öğretim Yöntemleri: Soru-Cevap, Anlatım |
| 3 | Segmentation and object generation techniques | No advance preparation is necessary. | Öğretim Yöntemleri: Anlatım |
| 4 | Feature engineering in OBIA | No advance preparation is necessary. | Öğretim Yöntemleri: Anlatım |
| 5 | Artificial neural networks (ANN) | No advance preparation is necessary. | Öğretim Yöntemleri: Anlatım |
| 6 | Deep learning methods (CNN, RNN) | No advance preparation is necessary. | Öğretim Yöntemleri: Anlatım |
| 7 | Mixed pixel classification | No advance preparation is necessary. | Öğretim Yöntemleri: Anlatım |
| 8 | Mid-Term Exam | Advance preparation is necessary. | Ölçme Yöntemleri: Proje / Tasarım, Portfolyo, Yazılı Sınav, Ödev |
| 9 | Spectral angle mapping and nonlinear classifiers | No advance preparation is necessary. | Öğretim Yöntemleri: Anlatım |
| 10 | Ensemble methods and multiple classifiers | No advance preparation is necessary. | Öğretim Yöntemleri: Anlatım |
| 11 | Classification of temporal image series | No advance preparation is necessary. | Öğretim Yöntemleri: Anlatım |
| 12 | Multi-source data integration | No advance preparation is necessary. | Öğretim Yöntemleri: Anlatım |
| 13 | Accuracy enhancement strategies and error sources | No advance preparation is necessary. | Öğretim Yöntemleri: Anlatım |
| 14 | Practical classification exercises | No advance preparation is necessary. | Öğretim Yöntemleri: Anlatım |
| 15 | Project presentations and overall evaluation | No advance preparation is necessary. | Öğretim Yöntemleri: Anlatım |
| 16 | Term Exams | Advance preparation is necessary. | Ölçme Yöntemleri: Ödev, Portfolyo, Proje / Tasarım, Yazılı Sınav |
| 17 | Term Exams | Advance preparation is necessary. | Ölçme Yöntemleri: Yazılı Sınav, Proje / Tasarım |
Student Workload - ECTS
| Works | Number | Time (Hour) | Workload (Hour) |
|---|---|---|---|
| Course Related Works | |||
| Class Time (Exam weeks are excluded) | 15 | 3 | 45 |
| Out of Class Study (Preliminary Work, Practice) | 15 | 4 | 60 |
| Assesment Related Works | |||
| Homeworks, Projects, Others | 1 | 20 | 20 |
| Mid-term Exams (Written, Oral, etc.) | 1 | 10 | 10 |
| Final Exam | 1 | 15 | 15 |
| Total Workload (Hour) | 150 | ||
| Total Workload / 25 (h) | 6,00 | ||
| ECTS | 6 ECTS | ||